Triple
T8558937
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roja |
E202642
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Pankaj Kapur |
E280419
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Pankaj Kapur | Statement: [Roja, starring, Pankaj Kapur]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pankaj Kapur Context triple: [Roja, starring, Pankaj Kapur]
-
A.
Pankaj Kapur
chosen
Pankaj Kapur is an acclaimed Indian actor and director known for his powerful performances in film, television, and theatre.
-
B.
Vikas Khanna
Vikas Khanna is an acclaimed Indian chef, restaurateur, cookbook author, and filmmaker known for his Michelin-starred cooking and appearances on culinary television shows.
-
C.
Deepak Kapur
Deepak Kapur is a computer scientist known for his influential work in automated reasoning and term rewriting systems.
-
D.
Sanjay Kapoor
Sanjay Kapoor is an Indian film and television actor and producer known for his work in Hindi cinema since the 1990s.
-
E.
Randhir Kapoor
Randhir Kapoor is an Indian actor, director, and producer from the prominent Kapoor film family, known for his work in Hindi cinema since the 1970s.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ca8326e6c881908ff720d6abaebdc5 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe9485dd88190bc2cf2adf39d48ee |
completed | March 31, 2026, 3:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf280edb288190a7db5486cc426253 |
completed | April 3, 2026, 2:38 a.m. |
Created at: March 30, 2026, 6:20 p.m.